Meaning of '8' and '4'

[phellonchen]

                    for j in range(8):
                        cur_image_features = image_features[cur_image_idx+j*4]
                        cur_new_input_embeds.append(cur_image_features)
                        cur_new_labels.append(torch.full((cur_image_features.shape[0],), IGNORE_INDEX, device=cur_labels.device, dtype=cur_labels.dtype))

what is the meaning of '8' and '4'?

[zyddnys]

i got the same issue, if there's only one input image i then image_features shape is [8, 64, 5120], so cur_image_idx+j*4 will lead to out of bound

[guozonghao96]

Our repository has been fully improved, and almost all bugs have been eliminated. For details, please refer to the main branch and the LLaVA-UHD v1 branch. This issue is now closed. If there are any new problems, feel free to open a new issue.